Instructions to use SystemAdmin123/TinyLLama-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SystemAdmin123/TinyLLama-v0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SystemAdmin123/TinyLLama-v0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SystemAdmin123/TinyLLama-v0")
model = AutoModelForCausalLM.from_pretrained("SystemAdmin123/TinyLLama-v0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SystemAdmin123/TinyLLama-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SystemAdmin123/TinyLLama-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/TinyLLama-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SystemAdmin123/TinyLLama-v0

SGLang

How to use SystemAdmin123/TinyLLama-v0 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SystemAdmin123/TinyLLama-v0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/TinyLLama-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SystemAdmin123/TinyLLama-v0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/TinyLLama-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SystemAdmin123/TinyLLama-v0 with Docker Model Runner:
```
docker model run hf.co/SystemAdmin123/TinyLLama-v0
```

SystemAdmin123 commited on Feb 7, 2025

Commit

ed5b375

verified ·

1 Parent(s): 7cd62b8

Training in progress, step 100

Browse files

Files changed (3) hide show

axolotl_config.yaml +13 -7
model.safetensors +1 -1
training_args.bin +2 -2

axolotl_config.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
 base_model: Maykeye/TinyLLama-v0
-batch_size: 32
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
@@ -13,29 +13,35 @@ datasets:
     no_input_format: '{instruction}'
     system_format: '{system}'
     system_prompt: ''
-eval_steps: 20
 flash_attention: true
-gpu_memory_limit: 80GiB
 group_by_length: true
 hub_model_id: SystemAdmin123/TinyLLama-v0
 hub_strategy: checkpoint
 learning_rate: 0.0002
 logging_steps: 10
 lr_scheduler: cosine
-max_steps: 2500
-micro_batch_size: 2
 model_type: AutoModelForCausalLM
 num_epochs: 100
 optimizer: adamw_bnb_8bit
-output_dir: /root/.sn56/axolotl/outputs/TinyLLama-v0
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
-save_steps: 40
 save_total_limit: 1
 sequence_len: 2048
 special_tokens:
   pad_token: </s>
 tokenizer_type: LlamaTokenizerFast
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''

 base_model: Maykeye/TinyLLama-v0
+batch_size: 128
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
     no_input_format: '{instruction}'
     system_format: '{system}'
     system_prompt: ''
+device_map: auto
+eval_sample_packing: false
+eval_steps: 200
 flash_attention: true
+gradient_checkpointing: true
 group_by_length: true
 hub_model_id: SystemAdmin123/TinyLLama-v0
 hub_strategy: checkpoint
 learning_rate: 0.0002
 logging_steps: 10
 lr_scheduler: cosine
+max_steps: 10000
+micro_batch_size: 32
 model_type: AutoModelForCausalLM
 num_epochs: 100
 optimizer: adamw_bnb_8bit
+output_dir: /root/.sn56/axolotl/tmp/TinyLLama-v0
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
+sample_packing: true
+save_steps: 200
 save_total_limit: 1
 sequence_len: 2048
 special_tokens:
   pad_token: </s>
 tokenizer_type: LlamaTokenizerFast
+torch_dtype: bf16
+training_args_kwargs:
+  hub_private_repo: true
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad456f579311a0f5eb96bbef4cbf70a4e5eeec10c557f40792d944631dd9d796
 size 9250704

 version https://git-lfs.github.com/spec/v1
+oid sha256:319278c870d9a5ea4178fca00222c5beeba5f93cdf8be6bc64256c87594b8647
 size 9250704

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10220c4137ea48c69f7a997accbc718211651f88c44fd5064aaf86fc05beb658
-size 6712

 version https://git-lfs.github.com/spec/v1
+oid sha256:49d83a9a919016b89c2e22a0a9e1bea7cd88625f15ca678835191dd97e6ead48
+size 6840